Current MaaS architecture, documentation and examples still fails to adequately convey the complexities and security risks involved in configuring the Gateway in a model-serving context. 

This affects any model served with MaaS and/or llm-d. Both Red Hat and Customer environments are likely highly vulnerable. A user with standard permissions can intercept, read, log, and alter all MaaS model traffic (including access keys, input prompts, and outputs).
A standard user in a namespace authorized to use the MaaS Gateway (which is any namespace in our default configuration and all the examples) can easily hijack any traffic going through MaaS. Same applied to llm-s.